Sparse-to-Dense

This repo implements the training and testing of deep regression neural networks for "Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image" by Fangchang Ma and Sertac Karaman at MIT. A video demonstration is available on YouTube. This repo offers the original implementation of the paper in Torch. The PyTorch version can be found here.

This repo can be used for training and testing of

• RGB (or grayscale image) based depth prediction
• sparse depth based depth prediction
• RGBd (i.e., both RGB and sparse depth) based depth prediction

Contents

0. Requirements
1. Training
2. Testing
3. Trained Models
4. Benchmark
5. Citation

Requirements

See the installation instructions for a step-by-step guide.

• Install Torch on a machine with CUDA GPU.
• Install cuDNN(v4 or above) and the Torch cuDNN bindings
• If you already have both Torch and cuDNN installed, update packages and install dependencies.

   luarocks install nn
   luarocks install cunn
   luarocks install cudnn
   luarocks install optnet

• Install the HDF5 format libraries. Files in our pre-processed datasets are in HDF5 formats.

   sudo apt-get update
   sudo apt-get install -y libhdf5-serial-dev hdf5-tools
   git clone https://github.com/davek44/torch-hdf5.git
   cd torch-hdf5
   luarocks make
   cd ..

• Download the preprocessed NYU Depth V2 and/or KITTI datasets in HDF5 formats and place them under the data folder. The downloading process might take an hour or so. The NYU dataset requires 32G of storage space, and KITTI requires 81G.

   cd data
   wget http://datasets.lids.mit.edu/sparse-to-dense/data/kitti.tar.gz
   tar -xvf kitti.tar.gz && rm -f kitti.tar.gz
   wget http://datasets.lids.mit.edu/sparse-to-dense/data/nyudepthv2.tar.gz 
   tar -xvf nyudepthv2.tar.gz && rm -f nyudepthv2.tar.gz 
   cd ..

• Download the networks pretrained on ImageNet datasets. In particular, use ResNet-50 for the NYU Depth V2 dataset, and ResNet-18 for the KITTI dataset. Place them under the pretrained folder.

   cd pretrained
   wget https://d2j0dndfm35trm.cloudfront.net/resnet-50.t7
   wget https://d2j0dndfm35trm.cloudfront.net/resnet-18.t7
   cd ..

Training

The training scripts come with several options, which can be listed with the --help flag.

th main.lua --help

To run the training, simply run main.lua. By default, the script runs the RGB-based prediction network on NYU-Depth-V2 with 1 GPU and 2 data-loader threads without using pretrained weights.

th main.lua 

To train networks with different datasets, input modalities, loss functions, and components, see the example below:

th main.lua -dataset kitti -inputType rgbd -nSample 100 -criterion l1 -encoderType conv -decoderType upproj -pretrain true

Training results will be saved under the results folder.

Model Options

Parameter	Options	Remarks
datasets	nyudepthv2, kitti
inputType	rgb, rgbd, d, g, gd	d:sparse depth only; g: grayscale
nSample	non-negative integer (0 for rgb and g)
criterion	l1, l2, berhu
pretrain	false, true
rep	linear, log, inverse	representation of input depth
encoderType	conv, depthsep, channeldrop	depthsep: depthwise separable convolution
decoderType	upproj, upconv, deconv2, deconv3	deconv_n: transposed convolution with kernel size n-by-n

Testing

To test the performance of a trained model, simply run main.lua with the -testOnly true option, along with other model options. For instance,

th main.lua -testOnly true -dataset kitti -inputType rgbd -nSample 100 -criterion l1 -encoderType conv -decoderType upproj -pretrain true

Trained Models

Download our trained models at http://datasets.lids.mit.edu/sparse-to-dense/results/ to the results folder. For instance,

cd results
wget -r -np -nH --cut-dirs=2 --reject "index.html*" http://datasets.lids.mit.edu/sparse-to-dense/results/nyudepthv2.input=rgbd.nsample=200.rep=linear.encoder=conv.decoder=upproj.criterion=l1.lr=0.01.bs=16.pretrained=true/
cd ..

More trained models will be released.

Benchmark

• Error metrics on NYU Depth v2:

  RGB	rms	rel	delta1	delta2	delta3
  Roy & Todorovic (CVPR 2016)	0.744	0.187	-	-	-
  Eigen & Fergus (ICCV 2015)	0.641	0.158	76.9	95.0	98.8
  Laina et al (3DV 2016)	0.573	0.127	81.1	95.3	98.8
  Ours-RGB	0.514	0.143	81.0	95.9	98.9

  RGBd-#samples	rms	rel	delta1	delta2	delta3
  Liao et al (ICRA 2017)-225	0.442	0.104	87.8	96.4	98.9
  Ours-20	0.351	0.078	92.8	98.4	99.6
  Ours-50	0.281	0.059	95.5	99.0	99.7
  Ours-200	0.230	0.044	97.1	99.4	99.8

  

• Error metrics on KITTI dataset:

  RGB	rms	rel	delta1	delta2	delta3
  Make3D	8.734	0.280	60.1	82.0	92.6
  Mancini et al (IROS 2016)	7.508	-	31.8	61.7	81.3
  Eigen et al (NIPS 2014)	7.156	0.190	69.2	89.9	96.7
  Ours-RGB	6.266	0.208	59.1	90.0	96.2

  RGBd-#samples	rms	rel	delta1	delta2	delta3
  Cadena et al (RSS 2016)-650	7.14	0.179	70.9	88.8	95.6
  Ours-50	4.884	0.109	87.1	95.2	97.9
  Liao et al (ICRA 2017)-225	4.50	0.113	87.4	96.0	98.4
  Ours-100	4.303	0.095	90.0	96.3	98.3
  Ours-200	3.851	0.083	91.9	97.0	98.6
  Ours-500	3.378	0.073	93.5	97.6	98.9

  

  Note: our networks are trained on the KITTI odometry dataset, using only sparse labels from laser measurements.

Citation

If you use our code or method in your work, please consider citing the following:

@article{Ma2017SparseToDense,
	title={Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image},
	author={Ma, Fangchang and Karaman, Sertac},
	booktitle={ICRA},
	year={2018}
}
@article{ma2018self,
	title={Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera},
	author={Ma, Fangchang and Cavalheiro, Guilherme Venturelli and Karaman, Sertac},
	journal={arXiv preprint arXiv:1807.00275},
	year={2018}
}

Please direct any questions to Fangchang Ma at fcma@mit.edu.